Associative embeddings for large-scale knowledge transfer with self-assessment

2013-12-11 · CVPR 2014 6 · Alexander Vezhnevets, Vittorio Ferrari

We propose a method for knowledge transfer between semantically related classes in ImageNet. By transferring knowledge from the images that have bounding-box annotations to the others, our method is capable of automatically populating ImageNet with many more bounding-boxes and even pixel-level segmentations. The underlying assumption that objects from semantically related classes look alike is formalized in our novel Associative Embedding (AE) representation. AE recovers the latent low-dimensional space of appearance variations among image windows. The dimensions of AE space tend to correspond to aspects of window appearance (e.g. side view, close up, background). We model the overlap of a window with an object using Gaussian Processes (GP) regression, which spreads annotation smoothly through AE space. The probabilistic nature of GP allows our method to perform self-assessment, i.e. assigning a quality estimate to its own output. It enables trading off the amount of returned annotations for their quality. A large scale experiment on 219 classes and 0.5 million images demonstrates that our method outperforms state-of-the-art methods and baselines for both object localization and segmentation. Using self-assessment we can automatically return bounding-box annotations for 30% of all images with high localization accuracy (i.e.~73% average overlap with ground-truth).

📄 PDF Abstract BibTeX arXiv:1312.3240

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processes Object Localization Transfer Learning

Methods 이 논문이 사용한 방법론

AE An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation…

Holographic Embeddings of Knowledge Graphs

2015-10-16 · Maximilian Nickel, Lorenzo Rosasco, Tomaso Poggio

Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn …

Knowledge Graphs Link Prediction Relational Reasoning

Geometric Factual Recall in Transformers

2026-05-12 · Shauli Ravfogel, Gilad Yehudai, Joan Bruna, Alberto Bietti arxiv

How do transformer language models memorize factual associations? A common view casts internal weight matrices as associative memories over pairs of embeddings, requiring parameter counts that scale linearly with the num…

Time Series Domain Adaptation via Sparse Associative Structure Alignment

2020-12-22 · Ruichu Cai, Jiawei Chen, Zijian Li, Wei Chen 외

Domain adaptation on time series data is an important but challenging task. Most of the existing works in this area are based on the learning of the domain-invariant representation of the data with the help of restrictio…

Domain Adaptation Time Series Time Series Analysis

Distributed Hierarchical Temporal Memory with Shared Associative Memory for Cross-Entity Preemptive Warning

2026-06-30 · Pavia Bera, Jennifer Adorno, Sanjukta Bhanja arxiv

Anomaly detection in multivariate time series remains a critical challenge in large-scale distributed systems, where related entities may exhibit transferable precursor behavior prior to anomaly onset. Existing methods t…

Anomaly Detection

CMAL: A Novel Cross-Modal Associative Learning Framework for Vision-Language Pre-Training

2024-10-16 · Zhiyuan Ma, Jianjun Li, GuoHui Li, Kaiyan Huang

With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved. The success of VLP largely benefits from the inf…

Contrastive Learning